© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 8469
    Prev
    Next
    INDEX
    Explanations

    references to copyright and licensing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Copyright and rights statements

    np_acts-logits-general · gemini-2.0-flash

    copyright rights reserved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.84
     Jefus
    -0.81
    ſelf
    -0.76
    ſelves
    -0.76
     themſelves
    -0.75
     HasFactory
    -0.74
     uſe
    -0.69
     myſelf
    -0.68
     Diſ
    -0.68
     himſelf
    -0.67
    POSITIVE LOGITS
     الرياضيه
    0.79
    Datuak
    0.60
     flo
    0.56
    AndroidJUnit
    0.56
    ayar
    0.56
     المعيارى
    0.54
    issements
    0.52
    icznie
    0.52
     Mat
    0.51
     Behav
    0.50
    Activations Density 0.138%

    No Known Activations